Ahmed Elgammal

About

Ahmed Elgammal is a professor in the Department of Computer Science at Rutgers University. His research focuses on Artificial Intelligence, Computer Vision, and Intelligent Systems. He has been recognized for his work through various media features, including coverage in the Washington Post and CNN's GPS show, and has received awards such as the Outstanding Student Paper at AAAI-16. Professor Elgammal has also been awarded an NSF grant for his research. His contributions are well-regarded within the academic community, and he is actively involved in advancing the fields of AI and computer vision.

Research topics

• Artificial Intelligence
• Computer Science
• Computer engineering

Selected publications

• Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis

  International Conference on Learning Representations · 2021 · 109 citations

  Senior authorCorresponding

  Training Generative Adversarial Networks (GAN) on high-fidelity images usually requires large-scale GPU-clusters and a vast number of training images. In this paper, we study the few-shot image synthesis task for GAN with minimum computing cost. We propose a light-weight GAN structure that gains superior quality on 1024*1024 resolution. Notably, the model converges from scratch with just a few hours of training on a single RTX-2080 GPU, and has a consistent performance, even with less than 100 t…

  PublisherOA PDF

• Self-Supervised Sketch-to-Image Synthesis

  Proceedings of the AAAI Conference on Artificial Intelligence · 2021-05-18 · 34 citations

  articleOpen accessSenior author

  Imagining a colored realistic image from an arbitrary-drawn sketch is one of human capabilities that we eager machines to mimic. Unlike previous methods that either require the sketch-image pairs or utilize low-quantity detected edges as sketches, we study the exemplar-based sketch-to-image (s2i) synthesis task in a self-supervised learning manner, eliminating the necessity of the paired sketch data. To this end, we first propose an unsupervised method to efficiently synthesize line-sketches for…

  PublisherOA PDFDOI

• Sketch-to-Art: Synthesizing Stylized Art Images from Sketches

  Lecture notes in computer science · 2021-01-01 · 25 citations

  book-chapterSenior author
  PublisherDOI

• Towards Faster and Stabilized GAN Training for High-fidelity Few-shot\n Image Synthesis

  arXiv (Cornell University) · 2021-01-12 · 25 citations

  preprintOpen accessSenior author

  Training Generative Adversarial Networks (GAN) on high-fidelity images\nusually requires large-scale GPU-clusters and a vast number of training images.\nIn this paper, we study the few-shot image synthesis task for GAN with minimum\ncomputing cost. We propose a light-weight GAN structure that gains superior\nquality on 1024*1024 resolution. Notably, the model converges from scratch with\njust a few hours of training on a single RTX-2080 GPU, and has a consistent\nperformance, even with less than…

  PublisherOA PDFDOI

• MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation

  Lecture notes in computer science · 2024-11-09 · 14 citations

  book-chapter
  PublisherDOI

Recent grants

• CAREER: Generalized Separation of Style and Content on Nonlinear Manifolds with Application to Human Motion Analysis

  NSF · $500k · 2006–2013

• RI: Small: Collaborative Research: Detecting Abnormalities in Images

  NSF · $340k · 2013–2017

• RI: Medium: Collaborative Research: Write A Classifier: Learning Fine-Grained Visual Classifiers from Text and Images

  NSF · $510k · 2014–2021

Frequent coauthors

• Mohamed Elhoseiny

  50 shared

• Yizhe Zhu

  University of California, Irvine

  30 shared

• Babak Saleh

  28 shared

• Bingchen Liu

  25 shared

• Chan-Su Lee

  Yeungnam University

  24 shared

• Tarek El-Gaaly

  Meta (United States)

  16 shared

• Kunpeng Song

  16 shared

• Mohamed Elhoseiny

  King Abdullah University of Science and Technology

  16 shared

Education

• Ph.D., Computer Science

  Rutgers, The State University of New Jersey

Awards & honors

• Outstanding Student Paper at AAAI-16
• NSF grant

Similar researchers at Rutgers University

• Dimitris Metaxash-69
• Tomasz Imielinskih-46
• Kostas Bekrish-44